A method, computer system, and a computer program product for environment personalization is provided. The present invention may include initializing a profile of a user. The present invention may include defining a baseline within the profile of the user. The present invention may include tracking a plurality of user data. The present invention may include storing the tracked plurality of user data in a tracked user database. The present invention may lastly include optimizing an environmental condition based on the tracked plurality of user data.
Legal claims defining the scope of protection. Each claim is shown in both the original legal language and a plain English translation.
1. A method for environment personalization, the method comprising: initializing a profile of a user; defining a baseline within the profile of the user, wherein the baseline includes a temperature of the environment; tracking a plurality of user data by performing image recognition using a convolutional neural network and feature identification on the image that was recognized using a mel-frequency cepstral coefficient feature extraction method, and further performing speech recognition to identify an utterance of the user using the mel-frequency cepstral coefficient feature extraction method; storing the tracked plurality of user data in a tracked user database; and optimizing an environmental condition based on the tracked plurality of user data, by at least modifying the temperature of the environment based on the identified utterance of the user or the recognized image of the user.
This invention relates to environment personalization systems that adapt to user preferences by analyzing behavioral and environmental data. The system initializes a user profile and establishes a baseline, including ambient temperature settings. It then continuously tracks user data through image recognition using a convolutional neural network (CNN) and feature identification via mel-frequency cepstral coefficient (MFCC) feature extraction. Additionally, the system performs speech recognition to detect user utterances, also utilizing MFCC-based processing. Collected data, including recognized images and speech, is stored in a database. The system then optimizes environmental conditions, such as temperature, by adjusting settings based on the analyzed user data, including recognized speech commands or visual cues from the user. The goal is to dynamically personalize the environment to enhance user comfort and efficiency. The method integrates multimodal sensing (visual and auditory) with machine learning to create an adaptive environment that responds to user behavior and explicit commands.
2. The method of claim 1 , wherein the profile of the user includes a photograph, a voice sample, a daily habit, and a user preference.
A system and method for user profiling and authentication involves collecting and analyzing diverse user data to enhance personalization and security. The technology addresses the need for more comprehensive user identification and behavior tracking beyond basic credentials, improving both user experience and system security. The method captures and stores a user profile containing multiple data types, including a photograph, voice sample, daily habits, and user preferences. The photograph serves as a biometric identifier for visual recognition, while the voice sample enables voice-based authentication. Daily habits, such as routine activities or device usage patterns, provide behavioral insights for personalized recommendations and anomaly detection. User preferences, such as settings or content choices, further refine the system's ability to tailor interactions. By integrating these elements, the system enables multi-factor authentication, reducing reliance on passwords and enhancing security. Additionally, the collected data supports adaptive personalization, allowing the system to anticipate user needs and improve engagement. The method ensures privacy by securely storing and processing the data while providing users with control over their information. This approach is applicable in various domains, including smart devices, digital assistants, and secure access systems.
3. The method of claim 1 , wherein the baseline is defined by the user within the profile of the user and is updated through the use of a machine learning algorithm.
A system and method for personalized data analysis involves establishing a baseline for a user's data, which is defined by the user within their profile and dynamically updated using a machine learning algorithm. The baseline serves as a reference point for evaluating subsequent data, allowing for comparisons and trend analysis. The machine learning algorithm continuously refines the baseline by analyzing new data inputs, ensuring it remains relevant and accurate over time. This adaptive approach enables the system to provide personalized insights, detect anomalies, and track changes in the user's data with high precision. The method is applicable in various domains, such as health monitoring, financial tracking, or performance analytics, where understanding deviations from a personalized baseline is critical. The machine learning algorithm may use techniques like regression, clustering, or time-series forecasting to update the baseline, depending on the nature of the data. The system ensures that the baseline remains aligned with the user's evolving patterns, improving the accuracy and relevance of the analysis.
4. The method of claim 1 , wherein the plurality of user data is collected by one or more mobile and/or internet connected internet of things (IoT) devices.
This invention relates to data collection systems using mobile and internet-connected Internet of Things (IoT) devices. The technology addresses the challenge of efficiently gathering and processing diverse user data from multiple sources to improve decision-making, personalization, or system optimization. The method involves collecting user data from a network of IoT devices, which may include smartphones, wearables, smart home appliances, or other connected sensors. These devices generate data such as location, usage patterns, environmental conditions, or biometric information. The collected data is then processed to extract meaningful insights, which can be used for applications like personalized recommendations, predictive maintenance, or adaptive system responses. The use of IoT devices ensures real-time data acquisition and broader coverage, enhancing the accuracy and relevance of the collected information. The system may also include data validation, filtering, or aggregation steps to ensure reliability and efficiency. By leveraging IoT devices, the method provides a scalable and flexible approach to data collection, enabling dynamic adaptation to user needs and environmental changes.
5. The method of claim 1 , wherein the plurality of user data is collected by an internet connected internet of things (IoT) camera, which is activated when a movement is detected in a field of view of the camera, and wherein a video analysis application programming interface (API) analyzes the plurality of user data collected by the camera.
This invention relates to a system for collecting and analyzing user data using an internet-connected Internet of Things (IoT) camera. The camera is activated when motion is detected within its field of view, capturing video or image data of the detected movement. The collected data is then processed by a video analysis application programming interface (API), which extracts relevant information from the captured content. The API may perform tasks such as object detection, motion tracking, or behavioral analysis to interpret the user data. The system enables automated monitoring and analysis of activities within the camera's field of view, providing insights or triggering actions based on the detected events. The IoT camera operates as part of a broader data collection framework, where the captured data is transmitted over the internet for further processing. The video analysis API enhances the functionality by enabling real-time or post-processing of the visual data, supporting applications in surveillance, security, or behavioral monitoring. The system ensures efficient data collection and analysis by leveraging motion-triggered activation, reducing unnecessary processing and storage requirements.
6. The method of claim 1 , wherein user data is stored in the tracked user database for a period of time defined by an administrative user within a web-accessible portal.
This invention relates to a system for managing user data in a web-accessible portal, addressing the need for controlled data retention in digital platforms. The system includes a tracked user database that stores user data, with retention periods configurable by an administrative user through a web interface. The administrative user can define how long user data remains in the database, ensuring compliance with privacy regulations or organizational policies. The system may also include a user interface for administrative users to set, modify, or enforce these retention periods, as well as mechanisms to automatically delete or archive data once the specified time has elapsed. The invention may further integrate with authentication systems to verify administrative privileges before allowing retention period adjustments. This approach provides flexibility in data management while maintaining security and regulatory adherence. The system may also include logging features to track changes to retention settings, ensuring accountability. The invention is particularly useful in applications requiring strict data governance, such as healthcare, finance, or enterprise software.
7. The method of claim 1 , wherein optimizing the environmental condition based on the tracked plurality of user data further comprises: learning a preference of the user based on the tracked plurality of user data; and adjusting the environmental condition based on the learned preferences of the user.
This invention relates to systems for optimizing environmental conditions in a space, such as a room or building, based on user preferences. The problem addressed is the lack of personalized and adaptive control of environmental factors like temperature, lighting, or air quality, which often rely on static settings or manual adjustments. The solution involves tracking user data, such as movement, presence, or interactions with environmental controls, to learn individual preferences and automatically adjust conditions accordingly. The system continuously monitors user behavior to refine these preferences over time, ensuring the environment adapts dynamically to the user's needs. For example, if a user consistently adjusts the thermostat to a specific temperature when present, the system learns this preference and proactively sets the temperature without manual input. The invention improves comfort, energy efficiency, and convenience by eliminating the need for repeated manual adjustments. The system may also integrate with other smart devices to create a cohesive, personalized environment. This approach is particularly useful in smart homes, offices, or healthcare settings where user comfort and efficiency are critical.
8. A computer system for environment personalization, comprising: one or more processors, one or more computer-readable memories, one or more computer-readable tangible storage medium, and program instructions stored on at least one of the one or more tangible storage medium for execution by at least one of the one or more processors via at least one of the one or more memories, wherein the computer system is capable of performing a method comprising: initializing a profile of a user; defining a baseline within the profile of the user; tracking a plurality of user data by performing image recognition using a convolutional neural network and feature identification on the image that was recognized using a mel-frequency cepstral coefficient feature extraction method, and further performing speech recognition to identify an utterance of the user using the mel-frequency cepstral coefficient feature extraction method; storing the tracked plurality of user data in a tracked user database; and optimizing an environmental condition based on the tracked plurality of user data, by at least modifying the temperature of the environment based on the identified utterance of the user or the recognized image of the user.
This invention relates to a computer system for personalizing environmental conditions based on user behavior and preferences. The system addresses the challenge of dynamically adjusting environmental settings to enhance user comfort and efficiency by leveraging machine learning and sensor data. The system includes processors, memory, and storage media with program instructions to initialize a user profile and establish a baseline for personalization. It tracks user data through image recognition using a convolutional neural network (CNN) and feature identification via mel-frequency cepstral coefficient (MFCC) feature extraction. Additionally, it performs speech recognition to identify user utterances using the same MFCC method. The collected data, including recognized images and speech, is stored in a database. The system optimizes environmental conditions by modifying parameters such as temperature based on the tracked data. For example, it adjusts temperature in response to recognized user speech or detected visual cues. The goal is to create a responsive environment that adapts to user needs in real time, improving comfort and productivity. The use of CNNs and MFCC-based feature extraction ensures accurate data processing for reliable personalization.
9. The computer system of claim 8 , wherein the profile of the user includes a photograph, a voice sample, a daily habit, and a user preference.
A computer system is designed to manage and utilize user profiles for personalized interactions. The system collects and stores detailed user profiles, which include a photograph, a voice sample, a daily habit, and a user preference. The photograph may be used for visual recognition or authentication, while the voice sample enables voice-based identification or command processing. The daily habit data allows the system to predict or adapt to the user's routine, and the user preference data enables customization of services or recommendations. The system may integrate these profile elements to enhance user experience, security, or efficiency in applications such as virtual assistants, authentication systems, or personalized service platforms. The inclusion of multiple profile types ensures comprehensive user modeling, improving accuracy and relevance in interactions. The system may also update or refine these profiles over time based on user behavior or explicit input. This approach addresses the need for more dynamic and context-aware user profiling in digital systems, reducing reliance on static or limited data sets. The system's ability to process and utilize diverse profile elements distinguishes it from simpler profiling methods that rely on a single data type.
10. The computer system of claim 8 , wherein the baseline is defined by the user within the profile of the user and is updated through the use of a machine learning algorithm.
A computer system is designed to monitor and analyze user behavior to detect anomalies, particularly in security or operational contexts. The system establishes a baseline of normal user behavior, which is defined by the user within their profile and dynamically updated using a machine learning algorithm. The baseline represents expected patterns of activity, such as login times, access frequencies, or transaction behaviors. The machine learning algorithm continuously refines this baseline by analyzing new data, adapting to changes in the user's behavior over time. When deviations from the baseline are detected, the system generates alerts or triggers automated responses to mitigate potential risks. This adaptive approach improves accuracy by reducing false positives and ensuring the baseline remains relevant as user behavior evolves. The system may also incorporate additional features, such as user authentication or activity logging, to enhance security and operational monitoring. The primary problem addressed is the need for a flexible, personalized baseline that adapts to individual user behavior without requiring manual updates, improving both security and usability.
11. The computer system of claim 8 , wherein the plurality of user data is collected by one or more mobile and/or internet connected internet of things (IoT) devices.
The invention relates to a computer system designed to collect and process user data from multiple sources, particularly focusing on data gathered by mobile and internet-connected Internet of Things (IoT) devices. The system addresses the challenge of efficiently aggregating and analyzing diverse user data to provide insights or services, such as personalized recommendations, security monitoring, or automated decision-making. The computer system includes a data collection module that retrieves user data from various IoT devices, such as smartphones, wearables, smart home appliances, or industrial sensors. These devices generate data related to user behavior, environmental conditions, or device performance. The system also incorporates a data processing module that organizes, filters, and analyzes the collected data to extract meaningful patterns or trends. Additionally, the system may include a user interface or output module to present the processed data in a usable format, such as reports, alerts, or automated actions. The invention ensures seamless integration with IoT devices, enabling real-time or periodic data collection while maintaining data security and privacy. The system is adaptable to different types of IoT devices and data formats, making it versatile for applications in healthcare, smart cities, industrial automation, or consumer electronics. By leveraging IoT-generated data, the system enhances decision-making processes and improves user experiences across various domains.
12. The computer system of claim 8 , wherein the plurality of user data is collected by an internet connected internet of things (IoT) camera, which is activated when a movement is detected in a field of view of the camera, and wherein a video analysis application programming interface (API) analyzes the plurality of user data collected by the camera.
A computer system collects and analyzes user data from an internet-connected Internet of Things (IoT) camera. The camera is activated when motion is detected within its field of view, capturing video data of the detected movement. The system includes a video analysis application programming interface (API) that processes the collected video data to extract relevant information. The API may perform tasks such as object detection, motion tracking, or behavioral analysis to interpret the captured footage. The system may also include additional components, such as a data storage module to store the collected and analyzed data, and a user interface to display the results. The camera may be part of a broader network of IoT devices that contribute to the data collection process. The system is designed to monitor and analyze user activity in real-time, providing insights or triggering automated responses based on the detected movements and analyzed data. The video analysis API ensures that the collected data is processed efficiently and accurately, enabling applications such as security monitoring, behavioral analysis, or smart environment management.
13. The computer system of claim 8 , wherein user data is stored in the tracked user database for a period of time defined by an administrative user within a web-accessible portal.
This invention relates to a computer system for managing user data, specifically addressing the need for controlled storage duration of user data in a web-accessible portal. The system includes a tracked user database that stores user data, with the storage period configurable by an administrative user through a web-accessible portal. The administrative user can define the duration for which user data remains in the database, ensuring compliance with data retention policies or privacy regulations. The system may also include a user interface for administrative users to set and modify these retention periods, as well as automated processes to enforce the deletion of data once the specified period expires. This ensures that user data is retained only as long as necessary, reducing storage costs and mitigating privacy risks. The system may further integrate with authentication mechanisms to verify administrative privileges before allowing modifications to data retention settings. The invention aims to provide a flexible and secure way to manage user data lifecycle within a web-based administrative framework.
14. The computer system of claim 8 , wherein optimizing the environmental condition based on the tracked plurality of user data further comprises: learning a preference of the user based on the tracked plurality of user data; and adjusting the environmental condition based on the learned preferences of the user.
A computer system monitors and adjusts environmental conditions, such as temperature, lighting, or air quality, based on user behavior and preferences. The system tracks multiple data points related to user interactions, such as time spent in a space, adjustments made to environmental controls, and user feedback. By analyzing this data, the system learns individual user preferences, such as preferred temperature ranges or lighting levels. The system then automatically adjusts the environmental conditions to align with these learned preferences, improving user comfort and efficiency. The system may also adapt over time as user behavior changes, ensuring continuous optimization. This approach eliminates the need for manual adjustments and enhances energy efficiency by tailoring environmental settings to user needs. The system can be applied in smart homes, offices, or other controlled environments where personalized comfort is desired.
15. A computer program product for environment personalization, comprising: one or more non-transitory computer-readable storage media and program instructions stored on at least one of the one or more tangible storage media, the program instructions executable by a processor to cause the processor to perform a method comprising: initializing a profile of a user; defining a baseline within the profile of the user; tracking a plurality of user data by performing image recognition using a convolutional neural network and feature identification on the image that was recognized using a mel-frequency cepstral coefficient feature extraction method, and further performing speech recognition to identify an utterance of the user using the mel-frequency cepstral coefficient feature extraction method; storing the tracked plurality of user data in a tracked user database; and optimizing an environmental condition based on the tracked plurality of user data, by at least modifying the temperature of the environment based on the identified utterance of the user or the recognized image of the user.
This invention relates to environment personalization systems that adapt to user preferences using machine learning and sensor data. The system initializes a user profile and establishes a baseline for environmental conditions. It tracks user data by analyzing images through a convolutional neural network (CNN) for feature identification, supplemented by mel-frequency cepstral coefficient (MFCC) feature extraction for both image and speech recognition. The system identifies user utterances via speech recognition, also using MFCC methods. Collected data is stored in a database. The system then optimizes environmental conditions, such as temperature, based on the tracked data, adjusting settings in response to recognized user actions, speech, or preferences inferred from the analyzed images. The goal is to dynamically personalize the environment by interpreting user behavior and explicit commands to enhance comfort and efficiency. The system combines visual and auditory analysis to create a responsive, adaptive environment tailored to individual needs.
16. The computer program product of claim 15 , wherein the profile of the user includes a photograph, a voice sample, a daily habit, and a user preference.
This invention relates to a computer program product for user authentication and personalization, addressing the need for secure and adaptive user identification in digital systems. The system collects and processes user-specific data to create a comprehensive profile, which includes a photograph, a voice sample, a daily habit, and a user preference. The photograph serves as a visual biometric identifier, while the voice sample provides an audio-based authentication method. Daily habits, such as login times or device usage patterns, are analyzed to detect anomalies and enhance security. User preferences, such as interface settings or content choices, are used to personalize the system's interactions. The profile is dynamically updated based on ongoing user behavior, ensuring continuous adaptation to changes in habits or preferences. This multi-faceted approach improves authentication accuracy and reduces reliance on single-factor verification methods. The system may also integrate with external databases or services to enrich the profile with additional contextual data, further refining personalization and security measures. By combining biometric, behavioral, and preference-based data, the invention provides a robust framework for secure and user-centric digital interactions.
17. The computer program product of claim 15 , wherein the baseline is defined by the user within the profile of the user and is updated through the use of a machine learning algorithm.
This invention relates to a computer program product for personalized data analysis, specifically addressing the challenge of dynamically adapting user-defined baselines in data monitoring systems. The system allows users to set a baseline within their profile, which serves as a reference point for evaluating subsequent data. The baseline is not static but is continuously updated using a machine learning algorithm, ensuring it remains relevant as user behavior, preferences, or external conditions change. The machine learning algorithm analyzes historical and real-time data to refine the baseline, improving accuracy and adaptability. This dynamic adjustment helps in detecting anomalies, trends, or deviations from expected behavior more effectively. The system may integrate with various data sources, such as user activity logs, sensor inputs, or external databases, to gather the necessary information for baseline refinement. The machine learning model may employ techniques like regression, clustering, or reinforcement learning to optimize the baseline over time. The invention enhances decision-making by providing a more accurate and context-aware reference for data comparison, reducing false positives in anomaly detection and improving system responsiveness to user needs.
18. The computer program product of claim 15 , wherein the plurality of user data is collected by one or more mobile and/or internet connected internet of things (IoT) devices.
The invention relates to a computer program product for processing and analyzing user data collected from mobile and internet-connected Internet of Things (IoT) devices. The technology addresses the challenge of efficiently gathering, storing, and analyzing large volumes of diverse user data generated by these devices to extract meaningful insights. The system includes a data collection module that retrieves user data from various sources, such as smartphones, wearables, smart home devices, and other IoT sensors. This data may include location information, usage patterns, environmental measurements, and behavioral metrics. The collected data is then processed and stored in a centralized database, where it is organized and prepared for analysis. The system further includes an analytics module that applies machine learning algorithms and statistical techniques to identify trends, anomalies, and correlations within the data. The results are used to generate reports, recommendations, or automated actions based on the insights derived. The invention aims to improve decision-making, personalization, and automation in applications such as healthcare, smart cities, industrial monitoring, and consumer behavior analysis. The use of IoT devices ensures real-time data collection and enhances the accuracy and relevance of the insights generated.
19. The computer program product of claim 15 , wherein the plurality of user data is collected by an internet connected internet of things (IoT) camera, which is activated when a movement is detected in a field of view of the camera, and wherein a video analysis application programming interface (API) analyzes the plurality of user data collected by the camera.
This invention relates to an internet-connected Internet of Things (IoT) camera system designed for automated data collection and analysis. The system addresses the challenge of efficiently capturing and processing user data in real-time environments, particularly in scenarios where continuous monitoring is impractical or resource-intensive. The IoT camera is configured to activate upon detecting movement within its field of view, ensuring energy-efficient operation by only recording when necessary. Once activated, the camera collects a plurality of user data, which may include video footage, motion patterns, or other relevant information. The collected data is then transmitted to a video analysis application programming interface (API), which processes the information to extract meaningful insights. The API may perform tasks such as object recognition, behavior analysis, or anomaly detection, depending on the specific application. This system is particularly useful in surveillance, smart home automation, or industrial monitoring, where automated, event-driven data collection and analysis are critical. The integration of IoT technology with video analysis APIs enables real-time decision-making and reduces the need for manual intervention, enhancing both efficiency and accuracy in data processing.
20. The computer program product of claim 15 , wherein optimizing the environmental condition based on the tracked plurality of user data further comprises: learning a preference of the user based on the tracked plurality of user data; and adjusting the environmental condition based on the learned preferences of the user.
This invention relates to optimizing environmental conditions in a space based on user preferences learned from tracked user data. The system monitors and records user behavior, physiological responses, and environmental conditions to identify patterns and preferences. By analyzing this data, the system learns individual or group preferences for conditions such as temperature, lighting, humidity, or air quality. The system then adjusts these environmental parameters in real-time to enhance user comfort, productivity, or well-being. The learning process involves machine learning or statistical modeling to refine preference predictions over time. The system may also adapt to changes in user behavior or external factors, ensuring continuous optimization. This approach improves energy efficiency and user satisfaction by personalizing environmental control without manual intervention. The invention is applicable in smart homes, offices, or other controlled environments where dynamic adjustment of conditions is beneficial.
Cooperative Patent Classification codes for this invention. Click any code to explore related patents in that topic.
June 3, 2019
March 15, 2022
Browse 5M+ US patents with plain-English claim translations and AI-generated analysis.